Date: Friday, 6 September 2024, 10:00 - 12:30 EEST
Event Recording
Speakers:
Eleftherios Christofi, PhD Student, CyI
Dr. Andreas Demou, Computational Scientist, CyI
Venue:
This training event is held as a hybrid event. You are welcome to join us at the Andreas Mouskos Auditorium, José Mariano Gago Hall, The Cyprus Institute. Otherwise please, connect to our live stream of the discussion, available on Zoom (Password: VsSCz1).
Description:
The introduction of physical insight into AI workflows for scientific and engineering applications enhances predictive accuracy and generalizability, thereby improving model reliability and enabling more realistic solutions. In recent years, many neural network frameworks have emerged, aiming to enforce underlying physics through different approaches, such as neural operators (NOs) and physics-informed neural networks (PINNs), among others. This training event aims to provide an overview of these various approaches, along with hands-on exercises, applying Physics informed Machine Learning methodologies to different fields of research, including molecular dynamics, microfluidics, and weather forecasting.
Language: English
Registration:
Registration for this event is open until Thursday, September 5th, 2024. Registration form here.
Pre-requisites:
Attendees should be familiar with at least one programming language, such as C/C++, Fortran, or Python, with some previous experience in AI. Hands-on exercises are part of the training and will be provided in Python.
Requirements:
On-site attendees should bring with them their own laptop to follow the hands-on practical.
Event Recording
Speakers:
Eleftherios Christofi, PhD Student, CyI
Dr. Andreas Demou, Computational Scientist, CyI
Venue:
This training event is held as a hybrid event. You are welcome to join us at the Andreas Mouskos Auditorium, José Mariano Gago Hall, The Cyprus Institute. Otherwise please, connect to our live stream of the discussion, available on Zoom (Password: VsSCz1).
Description:
The introduction of physical insight into AI workflows for scientific and engineering applications enhances predictive accuracy and generalizability, thereby improving model reliability and enabling more realistic solutions. In recent years, many neural network frameworks have emerged, aiming to enforce underlying physics through different approaches, such as neural operators (NOs) and physics-informed neural networks (PINNs), among others. This training event aims to provide an overview of these various approaches, along with hands-on exercises, applying Physics informed Machine Learning methodologies to different fields of research, including molecular dynamics, microfluidics, and weather forecasting.
Language: English
Registration:
Registration for this event is open until Thursday, September 5th, 2024. Registration form here.
Pre-requisites:
Attendees should be familiar with at least one programming language, such as C/C++, Fortran, or Python, with some previous experience in AI. Hands-on exercises are part of the training and will be provided in Python.
Requirements:
On-site attendees should bring with them their own laptop to follow the hands-on practical.
Agenda
10:00 - 10:30
Dr. Andreas Demou
Introduction to Physics Informed Machine Learning
10:30 - 11:00
Dr. Eleftherios Christofi
Application of PINNs in molecular dynamics
11:00 - 11:15
Coffee break
Coffee break
11:15 - 12:15
Dr. Andreas Demou
Hands-on exercises using the Fourier Neural Operator for microfluidics applications
12:15 - 12:30
Coffee break
Coffee break